© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 7812
    Prev
    Next
    INDEX
    Explanations

    durations of time expressed in minutes and seconds

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and details in programming or documentation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.65
    SpaceEngineers
    -0.62
    PUT
    -0.58
    Frameworks
    -0.58
     perspect
    -0.56
    EStreamFrame
    -0.56
    Download
    -0.55
    Store
    -0.55
    Tour
    -0.55
    Visit
    -0.54
    POSITIVE LOGITS
     22
    1.65
     15
    1.64
     31
    1.64
     33
    1.64
     14
    1.63
     16
    1.63
     23
    1.62
     17
    1.62
     34
    1.62
     32
    1.62
    Activations Density 0.242%

    No Known Activations